How enabling two settings tripled our scores on the ARC-AGI-3 benchmark

How two API settings improved GPT-5.6 performance on ARC-AGI-3, boosting scores and efficiency by retaining reasoning and enabling compaction.

01 / Measurement

Signal strength

Reality6.5 / 10

A primary source has published this claim or result; the editorial team has not independently validated it yet.

Singularity Pressure3.7 / 10

Potential leverage if the reported result scales or generalises; this is not a probability of singularity.

Confidence76%

Confidence reflects the available evidence and verification status: primary source.

Editorial interpretation

Why it matters

This is a capability signal because it tests a measurable change in what frontier systems can solve, retain or generalise. Its wider significance remains conditional on the evidence described below.

Evidence boundary

Evidence

Claim in the record

How enabling two settings tripled our scores on the ARC-AGI-3 benchmark

What is demonstrated

A primary source has published this claim or result; the editorial team has not independently validated it yet.

Primary source

OpenAIResearch institution · primary source

Open source ↗

Friction / doubt

Counterpoint

Independent replication, generalisation and downstream impact remain unverified.

Update conditions

What would change our mind

Independent evidence, reproducible evaluation, deployment data or credible corroboration.